Katsuya Hyodo's Projects
Special Presentation Demo at Intel IoT Planet 2021 DeepLearning Day / インテル IoT プラネット 2021 DeepLearning Dayの特別講演の発表資料 https://www.intel.co.jp/content/www/jp/ja/now/iot-planet/deep-learning-day.html
Official Pytorch implementation of 6DRepNet: 6D Rotation representation for unconstrained head pose estimation.
AMBER: Automated annotation and Multimodal Bag Extraction for Robotics
A tool to mask hard copies of Ubuntu terminals with specified keywords.
A curated list of awesome MediaPipe related code examples, libraries and software
Bazel's pre-built binaries for armv7l / aarch64 / x86_64.
Baba algorithm for robustly determining status changes of objects to be tracked.
TensorFlow, TensorFlow-Lite Benchmarks
The official repository for BEVerse
Release of Bayesian Filtering Library for ROS
Maintains a bond (i.e. heart beat ) between ROS nodes and provides feedback when the bond is broken
BoT-SORT + YOLOX implemented using only onnxruntime, Numpy and scipy, without cython_bbox and PyTorch. Fast human tracker. OSNet is not used.
Build-related tools for TensorFlow
ByteTrack: Multi-Object Tracking by Associating Every Detection Box
Categorical Depth Distribution Network for Monocular 3D Object Detection (CVPR 2021 Oral)
Provides Fetch integration for Cartographer.
ROS-independent library for dynamic class (i.e. plugin) introspection and loading from runtime libraries
[PyTorch] ClipCap for Japanese (日本語で学習・推論)
The official implementation of "CLRerNet: Improving Confidence of Lane Detection with LaneIoU"
[WIP] ONNX parts yard. The various operations described in Operator Schemas are converted in advance into OP stand-alone ONNX files.
YOLOv7 training. Generates a head-only dataset in YOLO format. The labels included in the CrowdHuman dataset are Head and FullBody, but ignore FullBody.
Config files for my GitHub profile.
Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.
DBFace is a real-time, single-stage detector for face detection, with faster speed and higher accuracy
This is tensorflow implementation for paper "Deep Image Matting"
The convertor/conversion of deep learning models for different deep learning frameworks/softwares.